qmd

Search markdown repositories with QMD ranked retrieval and rg fallback.

Updated Jan 23, 2026
One-click install
npx skills add https://github.com/paradox123/shared-ai-docs --skill qmd-paradox123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qmd
Source: https://github.com/paradox123/shared-ai-docs/tree/main/skills-repo/skills/qmd
Command: npx skills add https://github.com/paradox123/shared-ai-docs --skill qmd-paradox123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Locating relevant information across numerous markdown notes and documentation is slow and error-prone when done manually.

Core Features & Use Cases

  • Ranked retrieval across markdown-heavy repositories to surface the most relevant definitions, snippets, and docs.
  • Automatic fallback to rg when QMD is unavailable, with explicit user messaging about the fallback.
  • MCP-friendly query support for structured searches and integration with chat-based workflows.

Quick Start

Ask QMD to search your markdown notes for a topic and return ranked results.

Frequently Asked Questions about qmd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search markdown documentation across multiple repositories with ranked results?

Markdown search across repositories uses QMD for ranked retrieval to surface relevant definitions and snippets. It returns ranked results from markdown-heavy repos and falls back to rg with explicit messaging when QMD is unavailable.

Does QMD search support semantic or vector-based queries for markdown notes?

QMD search supports lex, vec, and hyde query types for flexible markdown retrieval workflows. These query types enable structured searches and integration with chat-based MCP workflows across knowledge bases.

What happens if the QMD CLI or MCP server is not installed when searching markdown files?

Markdown search falls back to rg automatically when QMD is unavailable, providing explicit user messaging about the fallback. This ensures retrieval continues without interruption even if the QMD CLI or MCP server is missing.

Can I use this to find specific definitions and code snippets in my markdown knowledge base?

Finding definitions and snippets in a markdown knowledge base is the core use case for ranked retrieval. QMD searches markdown-heavy repositories to surface the most relevant documentation content based on your query.

What is the best way to integrate ranked markdown search into chat-based workflows?

Ranked markdown search integrates into chat workflows through MCP-friendly query support. Using the QMD MCP server with lex, vec, or hyde query types enables structured searches directly within chat-based retrieval workflows.